AI agents use move_email to create or update resources in Gmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gmail environment.
The tool modifies email metadata (label assignments) without permanently deleting data. Moving emails between folders/labels is a write operation that changes state but remains reversible.
From the tool's definition Tool description states 'Move an email to a different label/folder. Removes all existing location labels' — this modifies email organization state by changing label assignments, which is reversible through moving back to original labels.
Attacks that exploit this kind of access
Move an email to a different label/folder. Removes all existing location labels. It is categorised as a Write tool in the Gmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gmail MCP server in PolicyLayer and add a rule for move_email: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gmail. Nothing to install.
move_email is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the move_email rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for move_email. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
move_email is provided by the Gmail MCP server (ndungukamami-sketch/gmail-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →